taxonomy: more CIQUAL categories for ingredients (#9717)

* taxonomy: more CIQUAL categories for ingredients * taxonomy: more CIQUAL categories for ingredients * update tests
openfoodfacts · Feb 1, 2024 · 9093b69 · 9093b69
1 parent 46479c4
commit 9093b69
Show file tree

Hide file tree

Showing 28 changed files with 114 additions and 92 deletions.
diff --git a/taxonomies/ingredients.txt b/taxonomies/ingredients.txt
@@ -4048,6 +4048,9 @@ tr:Süt tozu
 vegan:en:no
 vegetarian:en:yes
 nova:en:3
+ciqual_proxy_food_code:en:19044
+ciqual_proxy_food_name:en:Milk, powder, semi-skimmed
+ciqual_proxy_food_name:fr:Lait en poudre, demi-écrémé
 
 <en:whole milk powder
 <en:milk from France
@@ -4459,6 +4462,8 @@ carbon_footprint_fr_foodges_ingredient:fr:Yaourt
 carbon_footprint_fr_foodges_value:fr:2.9
 vegetarian:en:yes
 vegan:en:no
+ciqual_proxy_food_code:en:19593
+ciqual_proxy_food_name:fr:Yaourt, lait fermenté ou spécialité laitière, nature
 
 <en:yogurt
 en:plain yogurt
@@ -14162,6 +14167,9 @@ wikidata:en:Q41534
 wikipedia:en:https://en.wikipedia.org/wiki/Starch
 vegan:en:yes
 vegetarian:en:yes
+ciqual_proxy_food_code:en:9510
+ciqual_proxy_food_name:en:Maize/corn starch
+ciqual_proxy_food_name:fr:Amidon de maïs ou fécule de maïs
 
 # ingredient/fr:fécules has 612 products in 5 languages @2019-01-25
 # usage:fr:fécules (dont blé)
@@ -22976,6 +22984,8 @@ wikidata:en:Q15645384
 carbon_footprint_fr_foodges_ingredient:fr:Semoule de blé dur
 carbon_footprint_fr_foodges_value:fr:0.6
 allergens:en: en:gluten
+ciqual_proxy_food_code:en:9410
+ciqual_proxy_food_name:fr:Farine de blé tendre ou froment T110
 
 <en:wheat
 en:sprouted wheat
@@ -26264,6 +26274,9 @@ vegan:en:yes
 vegetarian:en:yes
 carbon_footprint_fr_foodges_ingredient:fr:Farine de blé
 carbon_footprint_fr_foodges_value:fr:1.2
+ciqual_proxy_food_code:en:9410
+ciqual_proxy_food_name:fr:Farine de blé tendre ou froment T110
+
 
 # <en:compound
 <en:flour
@@ -30379,6 +30392,11 @@ vegan:en:yes
 vegetarian:en:yes
 # openfoodfacts:https://world.openfoodfacts.org/ingredient/glucose
 # 24682 products in 24 languages @2018-09-24
+# probably not a very good CIQUAL proxy
+ciqual_proxy_food_code:en:31016
+ciqual_proxy_food_name:en:Sugar, white
+ciqual_proxy_food_name:fr:Sucre blanc
+
 
 # nova:en:glucose-syrup
 <en:glucose
@@ -30422,9 +30440,10 @@ tr:glikoz şurubu, glukoz şurubu, glükoz şurubu
 # 32467 products in 29 languages @2018-09-24
 wikipedia:en:https://en.wikipedia.org/wiki/Glucose_syrup
 wikidata:en:Q14770547
-# probably not a very good proxy, but the closest one in Ciqual
-ciqual_proxy_food_code:31089
-ciqual_proxy_food_name:en:Syrup, agave
+# probably not a very good CIQUAL proxy
+ciqual_proxy_food_code:en:31016
+ciqual_proxy_food_name:en:Sugar, white
+ciqual_proxy_food_name:fr:Sucre blanc
 
 
 <en:glucose syrup
@@ -31112,6 +31131,9 @@ sr:dekstroza
 sv:dextros
 # openfoodfacts:https://world.openfoodfacts.org/ingredient/dextrose
 # 29818 products in 30 languages @2018-09-24
+ciqual_proxy_food_code:en:31016
+ciqual_proxy_food_name:en:Sugar, white
+ciqual_proxy_food_name:fr:Sucre blanc
 
 <en:dextrose
 en:organic dextrose
@@ -32273,6 +32295,9 @@ zh:可可粉
 # zh-hk:可可粉
 vegan:en:yes
 vegetarian:en:yes
+ciqual_proxy_food_code:en:18100
+ciqual_proxy_food_name:en:Cocoa powder, without sugar, powder, instant
+ciqual_proxy_food_name:fr:Cacao, non sucré, poudre soluble
 
 <en:cocoa
 fr:cacao cru
@@ -32484,6 +32509,9 @@ uk:Какао-порошок
 # nds-nl:Kakoupouder
 wikidata:en:Q1062396
 # ingredient/cocoa-powder has 4521 products in 23 languages @2019-05-25
+ciqual_food_code:en:18100
+ciqual_food_name:en:Cocoa powder, without sugar, powder, instant
+ciqual_food_name:fr:Cacao, non sucré, poudre soluble
 
 <en:cocoa powder
 fr:poudre de cacao cru
@@ -32492,9 +32520,6 @@ fr:poudre de cacao cru
 en:raw cacao powder, Instant cocoa powder without sugar
 de:Rohes Kakaopulver
 fr:Poudre de cacao brute, Cacao non sucré en poudre soluble
-ciqual_food_code:en:18100
-ciqual_food_name:en:Cocoa powder, without sugar, powder, instant
-ciqual_food_name:fr:Cacao, non sucré, poudre soluble
 
 <en:cocoa powder
 en:fat reduced cocoa powder, low-fat cocoa powder, low fat cocoa powder, cocoa powder with low fat content
@@ -36710,6 +36735,9 @@ carbon_footprint_fr_foodges_ingredient:fr:Abricot "Pays du Sud"
 carbon_footprint_fr_foodges_value:fr:1.1
 # 5160 in 25 @2021-09-12
 eurocode_2_group_3:en: 9.20.10
+ciqual_food_code:en:13000
+ciqual_food_name:en:Apricot, pitted, raw
+ciqual_food_name:fr:Abricot, dénoyauté, cru
 
 <en:apricot
 en:Bergeron Apricot
@@ -50021,7 +50049,9 @@ wikipedia:en:https://en.wikipedia.org/wiki/Celery
 # fr:celeri has 4877 products in 10 languages @2018-10-21
 carbon_footprint_fr_foodges_ingredient:fr:Céleri
 carbon_footprint_fr_foodges_value:fr:0.8
-eurocode_2_group_3:en: 8.20.10
+eurocode_2_group_3:en: 8.20.10	
+ciqual_proxy_food_code:en:20055
+ciqual_proxy_food_name:fr:Céleri-rave, cru
 
 <en:celery
 en:celery stalk
@@ -50032,6 +50062,7 @@ pl:seler naciowy, selera naciowego
 ciqual_food_code:en:20023
 ciqual_food_name:en:Celery stalk, raw
 ciqual_food_name:fr:Céleri branche, cru
+
 # 88 in 3 languages @2021-12-01
 
 <en:celery

diff --git a/tests/integration/expected_test_results/api_v3_product_write/patch-language-fields.json b/tests/integration/expected_test_results/api_v3_product_write/patch-language-fields.json
@@ -24,6 +24,7 @@
             "vegetarian" : "yes"
          },
          {
+            "ciqual_food_code" : "18100",
             "id" : "en:cocoa-powder",
             "percent_estimate" : 5,
             "percent_max" : 10,

diff --git a/tests/integration/expected_test_results/search_v1/search-no-filter.json b/tests/integration/expected_test_results/search_v1/search-no-filter.json
@@ -536,7 +536,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "en",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],
@@ -1318,7 +1318,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "en",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],
@@ -1990,7 +1990,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "en",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],
@@ -2762,7 +2762,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "es",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],
@@ -3674,7 +3674,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "es",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],
@@ -4612,7 +4612,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "en",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],

diff --git a/...cted_test_results/search_v1/search-tags-categories-without-ingredients-from-palm-oil.json b/...cted_test_results/search_v1/search-tags-categories-without-ingredients-from-palm-oil.json
@@ -608,7 +608,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "es",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],
@@ -1546,7 +1546,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "en",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],

diff --git a/...integration/expected_test_results/search_v1/search-without-ingredients-from-palm-oil.json b/...integration/expected_test_results/search_v1/search-without-ingredients-from-palm-oil.json
@@ -536,7 +536,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "en",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],
@@ -1318,7 +1318,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "en",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],
@@ -1990,7 +1990,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "en",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],
@@ -2762,7 +2762,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "es",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],
@@ -3674,7 +3674,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "es",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],
@@ -4612,7 +4612,7 @@
          "last_editor" : "tests",
          "last_modified_by" : "tests",
          "last_modified_t" : "--ignore--",
-      "last_updated_t" : "--ignore--",
+         "last_updated_t" : "--ignore--",
          "lc" : "en",
          "link" : "http://world.openfoodfacts.org/",
          "main_countries_tags" : [],

diff --git a/tests/unit/expected_test_results/attributes/en-maybe-vegan.json b/tests/unit/expected_test_results/attributes/en-maybe-vegan.json
@@ -627,6 +627,7 @@
    "food_groups_tags" : [],
    "ingredients" : [
       {
+         "ciqual_proxy_food_code" : "9510",
          "id" : "en:tapioca",
          "percent_estimate" : 66.6666666666667,
          "percent_max" : 100,
@@ -713,10 +714,9 @@
    "ingredients_with_unspecified_percent_n" : 3,
    "ingredients_with_unspecified_percent_sum" : 100,
    "ingredients_without_ciqual_codes" : [
-      "en:enzyme",
-      "en:tapioca"
+      "en:enzyme"
    ],
-   "ingredients_without_ciqual_codes_n" : 2,
+   "ingredients_without_ciqual_codes_n" : 1,
    "known_ingredients_n" : 7,
    "languages" : {},
    "languages_codes" : {},

diff --git a/tests/unit/expected_test_results/attributes/fr-palm-oil-free.json b/tests/unit/expected_test_results/attributes/fr-palm-oil-free.json
@@ -630,6 +630,7 @@
          "vegetarian" : "yes"
       },
       {
+         "ciqual_proxy_food_code" : "9410",
          "id" : "en:flour",
          "percent_estimate" : 18.75,
          "percent_max" : 50,
@@ -708,10 +709,9 @@
    "ingredients_with_unspecified_percent_n" : 4,
    "ingredients_with_unspecified_percent_sum" : 100,
    "ingredients_without_ciqual_codes" : [
-      "en:chocolate",
-      "en:flour"
+      "en:chocolate"
    ],
-   "ingredients_without_ciqual_codes_n" : 2,
+   "ingredients_without_ciqual_codes_n" : 1,
    "known_ingredients_n" : 6,
    "languages" : {},
    "languages_codes" : {},

diff --git a/...unit/expected_test_results/ecoscore/origins-of-ingredients-in-origins-field-multiple.json b/...unit/expected_test_results/ecoscore/origins-of-ingredients-in-origins-field-multiple.json
@@ -407,6 +407,7 @@
    ],
    "ingredients" : [
       {
+         "ciqual_food_code" : "13000",
          "id" : "en:apricot",
          "percent" : 60,
          "percent_estimate" : 60,
@@ -485,10 +486,8 @@
    "ingredients_with_specified_percent_sum" : 90,
    "ingredients_with_unspecified_percent_n" : 1,
    "ingredients_with_unspecified_percent_sum" : 10,
-   "ingredients_without_ciqual_codes" : [
-      "en:apricot"
-   ],
-   "ingredients_without_ciqual_codes_n" : 1,
+   "ingredients_without_ciqual_codes" : [],
+   "ingredients_without_ciqual_codes_n" : 0,
    "known_ingredients_n" : 10,
    "lc" : "en",
    "misc_tags" : [

diff --git a/tests/unit/expected_test_results/ecoscore/origins-of-ingredients-in-origins-field.json b/tests/unit/expected_test_results/ecoscore/origins-of-ingredients-in-origins-field.json
@@ -404,6 +404,7 @@
    ],
    "ingredients" : [
       {
+         "ciqual_food_code" : "13000",
          "id" : "en:apricot",
          "percent" : 60,
          "percent_estimate" : 60,
@@ -482,10 +483,8 @@
    "ingredients_with_specified_percent_sum" : 90,
    "ingredients_with_unspecified_percent_n" : 1,
    "ingredients_with_unspecified_percent_sum" : 10,
-   "ingredients_without_ciqual_codes" : [
-      "en:apricot"
-   ],
-   "ingredients_without_ciqual_codes_n" : 1,
+   "ingredients_without_ciqual_codes" : [],
+   "ingredients_without_ciqual_codes_n" : 0,
    "known_ingredients_n" : 10,
    "lc" : "en",
    "misc_tags" : [

diff --git a/tests/unit/expected_test_results/ecoscore/origins-of-ingredients-nested-2.json b/tests/unit/expected_test_results/ecoscore/origins-of-ingredients-nested-2.json
@@ -413,6 +413,7 @@
          "id" : "en:chocolate",
          "ingredients" : [
             {
+               "ciqual_proxy_food_code" : "18100",
                "id" : "en:cocoa",
                "percent_estimate" : 8.33333333333333,
                "percent_max" : 50,
@@ -522,11 +523,10 @@
    "ingredients_with_unspecified_percent_sum" : 100,
    "ingredients_without_ciqual_codes" : [
       "en:chocolate",
-      "en:cocoa",
       "en:e951",
       "en:sweetener"
    ],
-   "ingredients_without_ciqual_codes_n" : 4,
+   "ingredients_without_ciqual_codes_n" : 3,
    "known_ingredients_n" : 9,
    "lc" : "en",
    "misc_tags" : [